© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13422
    Prev
    Next
    INDEX
    Explanations

    commands and syntax related to scripting and programming in a computing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    shell script commands and syntax elements (like pipes, conditionals, variable assignments, and command operators).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.67
     AssemblyTitle
    -0.63
     invokingState
    -0.59
    TypedDataSet
    -0.57
    EndContext
    -0.50
    exitRule
    -0.49
     Sess
    -0.49
     MenuView
    -0.49
     HttpNotFound
    -0.49
    DoubleQuotes
    -0.48
    POSITIVE LOGITS
    echo
    0.57
     echo
    0.57
     cat
    0.52
    sudo
    0.45
    ./
    0.45
     cd
    0.43
    GEBURTSDATUM
    0.40
    cat
    0.40
     ./
    0.39
    python
    0.39
    Activations Density 0.400%

    No Known Activations